Temporal distribution of forecasted wind speed is important to assess wind capacity for wind-related
technology purposes. Regional wind energy estimation needs the development of wind pattern to monitor
and forecast temporal wind behaviour. Temporal wind in Malaysia mainly depends on monsoonal factor
that circulates yearly and each monsoon derives distinct character of wind. This paper aims to develop a
model of wind speed pattern from historical wind speed data. Then, the model was used to forecast 5-years
seasonal wind speed and identify temporal distribution. Wind speed model development and forecast
was performed by identifying the best combination of wind speed seasonal component using Seasonal
Auto-regressive and Moving Average (SARIMA) model. Thus, three distribution models, Lognormal,
Weibull and Gamma models, were exploited to further observe consistency using Kolmogorov-Smirnov
goodness-of-fit test. The best fit model to represent seasonal wind distribution in each monsoon season
at Pulau Langkawi, Malaysia, is Log-normal distribution (0.04679-0.108).